We present a simple, yet general method to detect fake videos displaying human subjects, generated via Deep Learning techniques. The method relies on gauging the complexity of heart rate dynamics as derived from the facial video streams through remote photoplethysmography (rPPG). Features analyzed have a clear semantics as to such physiological behaviour. The approach is thus explainable both in terms of the underlying context model and the entailed computational steps. Most important, when compared to more complex state-of-the-art detection methods, results so far achieved give evidence of its capability to cope with datasets produced by different deep fake models.

DeepFakes Have No Heart: A Simple rPPG-Based Method to Reveal Fake Videos / G. Boccignone, S. Bursic, V. Cuculo, A. D'Amelio, G. Grossi, R. Lanzarotti, S. Patania (LECTURE NOTES IN COMPUTER SCIENCE). - In: Image Analysis and Processing – ICIAP 2022 / [a cura di] S. Sclaroff, C. Distante, M. Leo, G.M. Farinella, F. Tombari. - [s.l] : Springer, 2022. - ISBN 978-3-031-06429-6. - pp. 186-195 (( convegno International Conference on Image Analysis and Processing tenutosi a Lecce nel 2022 [10.1007/978-3-031-06430-2_16].

DeepFakes Have No Heart: A Simple rPPG-Based Method to Reveal Fake Videos

G. Boccignone
Primo
;
S. Bursic
Secondo
;
V. Cuculo;A. D'Amelio
;
G. Grossi;R. Lanzarotti
Penultimo
;
S. Patania
Ultimo
2022

Abstract

We present a simple, yet general method to detect fake videos displaying human subjects, generated via Deep Learning techniques. The method relies on gauging the complexity of heart rate dynamics as derived from the facial video streams through remote photoplethysmography (rPPG). Features analyzed have a clear semantics as to such physiological behaviour. The approach is thus explainable both in terms of the underlying context model and the entailed computational steps. Most important, when compared to more complex state-of-the-art detection methods, results so far achieved give evidence of its capability to cope with datasets produced by different deep fake models.
DeepFake detection; rPPG; Image forensics; Biological signals
Settore INF/01 - Informatica
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
2022
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
ICIAP2021___DeepFake_detection.pdf

accesso aperto

Tipologia: Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione 4.32 MB
Formato Adobe PDF
4.32 MB Adobe PDF Visualizza/Apri
Boccignone2022_Chapter_DeepFakesHaveNoHeartASimpleRPP.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 681.68 kB
Formato Adobe PDF
681.68 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/930968
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 5
social impact